replicating the results - MAPE

[Sepidehabol]

Hello Prof. Lu!
I am trying to replicate the results in Fig S1 A for which I am running the validation_model("sigma_y", 10) varying the train size 10 to 20, 30, ..., 10,000 manually each time I run it.

My question is whether the MAPE on the y-axis in Fig S1 A is the mean value of the MAPE as the output of the validation_model. Running the model for tain_size=10 I get the mean value=1274.4625 which is not in the order of magnitude of MAPE in Fig S1 A. I have run it for tain_size up tp 100 and no close value to what it is in Fig S1 A. I would appreciate your response on this please.

Result:
sigma_y 10
1274.4625 689.9193

I have the same issue with Fig S1 B.

[Shatom]

I also run into the same problem.

[lululxvi]

Did you use the DeepXDE version mentioned at https://github.com/lululxvi/deep-learning-for-indentation#code?

[Sepidehabol]

Thank you. I am using version 1.1.2 and still getting very high mean values of MAPE.
Also, running the Validation_FEM (trying to replicate Fig 2B), the MAPE values are of the order 1000.
I appreciate your advice on this.

[Shatom]

Thank you, Lu lu. I am using the version 0.14.1.
I set the set standardize=True in dde.data.DataSet(), not the dde.data.MfDateSet(),
and it seems ok with MAPE under order 100, for both Fig S1 B and Fig 2 B.
Thank you for your information.

[Sepidehabol]

I did the same although my version is 1.1.2 and now it seems working. Thank you!

[lululxvi]

@Shatom Do you mean that you resolved the issue and it works?

[Shatom]

@lululxvi Yes.